From Classification to Full Object Interpretation
Lists
Only you see this
Abstract
In current classification schemes, the goal is usually to identify category instances in an image, together with their corresponding image locations. However, object recognition goes beyond top-level category labeling: when we see a known object, we not only recognize the complete object, but also identify and localize its parts and subparts at multiple levels. Identifying and localizing parts, called “object interpretation,” is often necessary for interacting with visible objects in the surrounding environment.
BibTeX
@inproceedings{ullman2009from,
author = {Shimon Ullman},
title = {{From Classification to Full Object Interpretation}},
booktitle = {Cambridge},
year = {2009},
doi = {10.1017/cbo9780511635465.016},
}Loading related content...